{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T00:39:06Z","timestamp":1760488746477,"version":"build-2065373602"},"reference-count":31,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T00:00:00Z","timestamp":1760400000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"The Science and Technology Research Program for the Education Department of Hubei province of China under Grant","award":["D20163101"],"award-info":[{"award-number":["D20163101"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>The role played by communication technology in daily life is gradually increasing. However, there are problems such as complex types of signals, huge amount of data and noise interference, and the recognition accuracy of existing modulation classification methods is low. Therefore, the study proposes a signal automatic modulation classification model based on fixed K-mean algorithm and denoising autoencoder. The model uses fixed K-mean algorithm for feature classification and optimizes median filtering algorithm using dynamic thresholding. The classifier is used to improve the recognition accuracy of specific signals, and long short-term memory and data random corruption denoising are used to optimize the autoencoder. The experiments indicated that the signal classification accuracy of the model were 17.6% and 16.8% higher than the other two models, respectively. The computational complexity of the improved model decreased dramatically, but the average classification accuracy was only 1.6% lower than that before the improvement. The communication overhead and training efficiency were better than the other models, and the number of parameters of the model was 1\/2 of that of the pre-improvement model. The memory occupancy and running time were reduced by 335KB and 33ms, respectively. Compared to the other two models, the model\u2019s average classification accuracy at a signal-to-noise ratio of 0 was 18.4% and 19.7% higher, respectively. As a result, the improved model effectively increases signal recognition accuracy, enhances model robustness, and significantly reduces computational complexity while ensuring real-time signal processing for communication computing.<\/jats:p>","DOI":"10.1371\/journal.pone.0333098","type":"journal-article","created":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T17:26:47Z","timestamp":1760462807000},"page":"e0333098","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Automatic modulation classification method using fixed K-means algorithm for feature clustering processing"],"prefix":"10.1371","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7637-598X","authenticated-orcid":true,"given":"Li","family":"Yuan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2025,10,14]]},"reference":[{"issue":"12","key":"pone.0333098.ref001","doi-asserted-by":"crossref","first-page":"13387","DOI":"10.1109\/TVT.2022.3196103","article-title":"Spatial-temporal hybrid feature extraction network for few-shot automatic modulation classification","volume":"71","author":"J Che","year":"2022","journal-title":"IEEE Trans Veh Technol"},{"issue":"5","key":"pone.0333098.ref002","doi-asserted-by":"crossref","first-page":"497","DOI":"10.1049\/cmu2.12269","article-title":"3D convolutional neural networks based automatic modulation classification in the presence of channel noise","volume":"16","author":"R Khan","year":"2021","journal-title":"IET Commun"},{"issue":"24","key":"pone.0333098.ref003","doi-asserted-by":"crossref","first-page":"24708","DOI":"10.1109\/JIOT.2022.3194508","article-title":"A lightweight decentralized-learning-based automatic modulation classification method for resource-constrained edge devices","volume":"9","author":"B Dong","year":"2022","journal-title":"IEEE Internet Things J"},{"issue":"8","key":"pone.0333098.ref004","doi-asserted-by":"crossref","first-page":"1804","DOI":"10.1109\/LCOMM.2022.3179003","article-title":"ConvLSTMAE: A spatiotemporal parallel autoencoders for automatic modulation classification","volume":"26","author":"S Yunhao","year":"2022","journal-title":"IEEE Commun Lett"},{"issue":"2","key":"pone.0333098.ref005","doi-asserted-by":"crossref","first-page":"674","DOI":"10.1109\/TR.2022.3161138","article-title":"Detection tolerant black-box adversarial attack against automatic modulation classification with deep learning","volume":"71","author":"P Qi","year":"2022","journal-title":"IEEE Trans Rel"},{"key":"pone.0333098.ref006","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TAES.2022.3189335","article-title":"Deep-learning hopping capture model for automatic modulation classification of wireless communication signals","author":"L Li","year":"2022","journal-title":"IEEE Trans Aerosp Electron Syst"},{"issue":"7","key":"pone.0333098.ref007","doi-asserted-by":"crossref","first-page":"7942","DOI":"10.1109\/TVT.2022.3164935","article-title":"Automatic modulation classification based on decentralized learning and ensemble learning.","volume":"71","author":"X Fu","year":"2022","journal-title":"IEEE Trans Veh Technol"},{"issue":"11","key":"pone.0333098.ref008","doi-asserted-by":"crossref","first-page":"1303","DOI":"10.1049\/cmu2.12335","article-title":"Automatic modulation classification using techniques from image classification","volume":"16","author":"Y Sun","year":"2022","journal-title":"IET Commun"},{"issue":"10","key":"pone.0333098.ref009","doi-asserted-by":"crossref","first-page":"8713","DOI":"10.1109\/TWC.2022.3168884","article-title":"A hierarchical classification head based convolutional gated deep neural network for automatic modulation classification","volume":"21","author":"S Chang","year":"2022","journal-title":"IEEE Trans Wireless Commun"},{"issue":"14","key":"pone.0333098.ref010","doi-asserted-by":"crossref","first-page":"12276","DOI":"10.1109\/JIOT.2023.3247162","article-title":"Automatic modulation classification via meta-learning","author":"X Hao","year":"2023","journal-title":"IEEE Internet Things J"},{"issue":"11","key":"pone.0333098.ref011","doi-asserted-by":"crossref","first-page":"162","DOI":"10.3390\/computers11110162","article-title":"Robust automatic modulation classification using convolutional deep neural network based on scalogram information","volume":"11","author":"AM Abdulkarem","year":"2022","journal-title":"Computers"},{"issue":"1","key":"pone.0333098.ref012","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1049\/sfw2.12032","article-title":"An improved K-means algorithm for big data.","volume":"16","author":"F Moodi","year":"2022","journal-title":"IET Softw"},{"issue":"3","key":"pone.0333098.ref013","doi-asserted-by":"crossref","first-page":"2745","DOI":"10.1007\/s11277-021-09028-4","article-title":"Improved K-means based Q learning algorithm for optimal clustering and node balancing in WSN","volume":"122","author":"M Sathyamoorthy","year":"2021","journal-title":"Wireless Pers Commun"},{"issue":"26","key":"pone.0333098.ref014","doi-asserted-by":"crossref","first-page":"37007","DOI":"10.1007\/s11042-021-11255-7","article-title":"Effects of similarity\/distance metrics on k-means algorithm with respect to its applications in IoT and multimedia: a review","volume":"81","author":"MK Gupta","year":"2021","journal-title":"Multimed Tools Appl"},{"issue":"6","key":"pone.0333098.ref015","doi-asserted-by":"crossref","first-page":"390","DOI":"10.3390\/drones7060390","article-title":"Automatic modulation classification using deep residual neural network with masked modeling for wireless communications","volume":"7","author":"Y Peng","year":"2023","journal-title":"Drones"},{"issue":"7","key":"pone.0333098.ref016","doi-asserted-by":"crossref","first-page":"574","DOI":"10.12720\/jcm.17.7.574-580","article-title":"Comparison of automatic modulation classification techniques.","volume":"17","author":"SA Jassim","year":"2022","journal-title":"J. Commun"},{"issue":"3","key":"pone.0333098.ref017","doi-asserted-by":"crossref","first-page":"549","DOI":"10.1109\/TCCN.2023.3252580","article-title":"Toward the automatic modulation classification with adaptive wavelet network","volume":"9","author":"J Zhang","year":"2023","journal-title":"IEEE Trans Cogn Commun Netw"},{"issue":"7","key":"pone.0333098.ref018","doi-asserted-by":"crossref","first-page":"4600","DOI":"10.1109\/TWC.2022.3227518","article-title":"High-order convolutional attention networks for automatic modulation classification in communication","volume":"22","author":"D Zhang","year":"2023","journal-title":"IEEE Trans Wireless Commun"},{"issue":"16","key":"pone.0333098.ref019","doi-asserted-by":"crossref","first-page":"7281","DOI":"10.3390\/s23167281","article-title":"Automatic modulation classification based on CNN-transformer graph neural network","volume":"23","author":"D Wang","year":"2023","journal-title":"Sensors (Basel)"},{"issue":"3","key":"pone.0333098.ref020","doi-asserted-by":"crossref","first-page":"891","DOI":"10.33395\/sinkron.v7i3.11458","article-title":"Superior class to improve student achievement using the K-means algorithm","volume":"7","author":"YH Syahputra","year":"2022","journal-title":"SinkrOn"},{"issue":"2","key":"pone.0333098.ref021","doi-asserted-by":"crossref","first-page":"474","DOI":"10.30574\/ijsra.2022.7.2.0309","article-title":"Initial centroid selection for K- means clustering algorithm using the statistical method","volume":"7","author":"N Sujatha","year":"2022","journal-title":"Int J Sci Res Arch"},{"issue":"5","key":"pone.0333098.ref022","doi-asserted-by":"crossref","first-page":"135","DOI":"10.23919\/JCC.ja.2022-0580","article-title":"A convolutional and transformer based deep neural network for automatic modulation classification","volume":"20","author":"S Ying","year":"2023","journal-title":"China Commun"},{"issue":"1","key":"pone.0333098.ref023","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1007\/s10660-021-09458-z","article-title":"RETRACTED ARTICLE: Innovative study on clustering center and distance measurement of K-means algorithm: mapreduce efficient parallel algorithm based on user data of JD mall","volume":"23","author":"Y Liu","year":"2021","journal-title":"Electron Commer Res"},{"key":"pone.0333098.ref024","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1007\/s13198-021-01262-0","article-title":"Research on image text recognition based on canny edge detection algorithm and k-means algorithm","volume":"13","author":"F Wu","year":"2021","journal-title":"Int J Syst Assur Eng Manag"},{"issue":"2","key":"pone.0333098.ref025","doi-asserted-by":"crossref","DOI":"10.1007\/s40866-024-00213-5","article-title":"A monitoring model for abnormal electricity consumption based on K-means++ clustering and improved K-nearest neighbor algorithm","volume":"9","author":"J Yang","year":"2024","journal-title":"Smart Grids Energy"},{"issue":"4","key":"pone.0333098.ref026","doi-asserted-by":"crossref","first-page":"3433","DOI":"10.1109\/TKDE.2022.3155450","article-title":"An effective and efficient algorithm for K-means clustering with new formulation.","volume":"35","author":"F Nie","year":"2022","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"1","key":"pone.0333098.ref027","doi-asserted-by":"crossref","first-page":"43","DOI":"10.47852\/bonviewAIA2202524","article-title":"Distribution alignment using complement entropy objective and adaptive consensus-based label refinement for partial domain adaptation","volume":"1","author":"S Choudhuri","year":"2023","journal-title":"AIA"},{"issue":"1","key":"pone.0333098.ref028","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1049\/cit2.12044","article-title":"Image\u2010denoising algorithm based on improved K\u2010singular value decomposition and atom optimization","volume":"7","author":"R Chen","year":"2021","journal-title":"CAAI Trans on Intel Tech"},{"issue":"1","key":"pone.0333098.ref029","doi-asserted-by":"crossref","first-page":"719","DOI":"10.1007\/s00521-022-07766-5","article-title":"Genetic algorithm to optimize the SVM and K-means algorithms for mapping of mineral prospectivity","volume":"35","author":"R Ghezelbash","year":"2022","journal-title":"Neural Comput Appl"},{"issue":"8","key":"pone.0333098.ref030","doi-asserted-by":"crossref","first-page":"5145","DOI":"10.3390\/app13085145","article-title":"A lightweight deep learning model for automatic modulation classification using residual learning and squeeze\u2013excitation blocks","volume":"13","author":"MZ Nisar","year":"2023","journal-title":"Appl Sci"},{"issue":"1","key":"pone.0333098.ref031","doi-asserted-by":"crossref","first-page":"964","DOI":"10.1109\/JSYST.2022.3207377","article-title":"Efficient convolutional networks for robust automatic modulation classification in OFDM-based wireless systems.","volume":"17","author":"T Huynh-The","year":"2022","journal-title":"IEEE Syst J"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0333098","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T17:26:52Z","timestamp":1760462812000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0333098"}},"subtitle":[],"editor":[{"given":"O-Joun","family":"Lee","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2025,10,14]]},"references-count":31,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2025,10,14]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0333098","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,14]]}}}